Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.10093 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915731649593344 |
|---|---|
| author | Qiu, Yiding Azimi, Seyed Mahdi Lensky, Artem |
| author_facet | Qiu, Yiding Azimi, Seyed Mahdi Lensky, Artem |
| contents | Large programming courses struggle to provide timely, detailed feedback on student code. We developed Mark My Works, a local autograding system that combines traditional unit testing with LLM-generated explanations. The system uses role-based prompts to analyze submissions, critique code quality, and generate pedagogical feedback while maintaining transparency in its reasoning process.
We piloted the system in a 191-student engineering course, comparing AI-generated assessments with human grading on 79 submissions. While AI scores showed no linear correlation with human scores (r = -0.177, p = 0.124), both systems exhibited similar left-skewed distributions, suggesting they recognize comparable quality hierarchies despite different scoring philosophies. The AI system demonstrated more conservative scoring (mean: 59.95 vs 80.53 human) but generated significantly more detailed technical feedback. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_10093 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Mark My Works Autograder for Programming Courses Qiu, Yiding Azimi, Seyed Mahdi Lensky, Artem Software Engineering Large programming courses struggle to provide timely, detailed feedback on student code. We developed Mark My Works, a local autograding system that combines traditional unit testing with LLM-generated explanations. The system uses role-based prompts to analyze submissions, critique code quality, and generate pedagogical feedback while maintaining transparency in its reasoning process. We piloted the system in a 191-student engineering course, comparing AI-generated assessments with human grading on 79 submissions. While AI scores showed no linear correlation with human scores (r = -0.177, p = 0.124), both systems exhibited similar left-skewed distributions, suggesting they recognize comparable quality hierarchies despite different scoring philosophies. The AI system demonstrated more conservative scoring (mean: 59.95 vs 80.53 human) but generated significantly more detailed technical feedback. |
| title | Mark My Works Autograder for Programming Courses |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2601.10093 |